Face recognition using scattering convolutional network

Abstract

Face recognition has been an active research area in the past few decades. In general, face recognition can be very challenging due to variations in viewpoint, illumination, facial expression, etc. Therefore it is essential to extract features which are invariant to some or all of these variations.Here a new image representation, called scattering transform/network, has been used to extract features from faces. The scattering transform is a kind of convolutional network which provides a powerful multi-layer representation for signals. After extraction of scattering features, PCA is applied to reduce the dimensionality of the data and then a multi-class support vector machine is used to perform recognition. The proposed algorithm has been tested on three face datasets and achieved a very high recognition rate.

An experimental study of deep convolutional features for iris recognition

“…Then some statistical features are extracted from each transform image, and features from all transformed images are concatenated to form the overall feature representation. The scattering network has also been used for biometric recognition in the past [29]- [31]. To illustrate how this network works, the output of the second layer of scattering network for a sample iris image is shown in Figure 3.…”

Near-Duplicate Image Detection System Using Coarse-to-Fine Matching Scheme Based on Global and Local CNN Features

“…Salvador et al [22] located the potential object regions in an image by employing the region proposal network (RPN) [42]. Besides these region detection algorithms, attention mechanisms have been introduced to capture local characteristics in image classification and facial expression recognition tasks [48,49,51]. Assaf et al [48] improved the classical Capsule Network (CapsNet) architecture by embedding the self-attention module between the convolutional layers and the primary CapsNet layers for image classification.…”

“…Assaf et al [48] improved the classical Capsule Network (CapsNet) architecture by embedding the self-attention module between the convolutional layers and the primary CapsNet layers for image classification. Shervin et al [49] proposed the spatial transformer network [50] to detect important face parts for facial expression recognition. Wang et al [51] built the residual attention network by stacking multiple attention modules within the feed forward network architecture for image classification.…”

“…Since only a single global CNN feature is extracted from each image, the coarse matching stage can efficiently filter most of the irrelevant images of a given query image to narrow the search scope largely. In the fine matching stage, motivated by the attention-based image classification and facial expression recognition works [48,49,51], we match the robust and stable local CNN features that are extracted from the regions surrounding the maximum values of CFMs and the saliency map generated by the graph-based visual saliency detection (GBVS) algorithm [52]. Consequently, the proposed approach can effectively and efficiently detect near-duplicate images of a given query from image databases.…”

“…(2) The saliency map-based local CNN features are extracted. In the tasks of facial expression recognition and image classification, the introduction of attention mechanisms leads to the significant improvements [48][49][50][51]. Motivated by these works, after the global CNN feature matching, we detect the saliency map by the graph-based visual saliency detection (GBVS) algorithm [52] and extract the local CNN features from the local regions surrounding the maximum values of the saliency map.…”